Management Science and Engineering

Permanent URI for this collectionhttps://uwspace.uwaterloo.ca/handle/10012/9910

This is the collection for the University of Waterloo's Department of Management Science and Engineering.

Research outputs are organized by type (eg. Master Thesis, Article, Conference Paper).

Waterloo faculty, students, and staff can contact us or visit the UWSpace guide to learn more about depositing their research.

Browse

Now showing 1 - 10 of 10

A Comparative Study of Univariate Time-series Methods for Sales Forecasting
(University of Waterloo, 2020-01-16) Shah, Vishvesh; Dimitrov, Stanko
Sales time-series forecasters, data scientists and managers often use timeseries forecasting methods to predict sales. Nonetheless, it is still a question which time-series method a forecaster is best off using, if they only have time to generate one forecast. This study investigates and evaluates different sales time-series forecasting methods: multiplicative Holt-Winters (HW), additive HW, Seasonal Auto Regressive Integrated Moving Average (SARIMA) (A variant of Auto Regressive Integrated Moving Average (ARIMA)), Long Short-Term Memory Recurrent Neural Networks (LSTM) and the Prophet method by Facebook on thirty-two univariate sales time-series. The data used to forecast sales is taken from time-series Data Library (TSDL). With respect to the Root Mean Square Error (RMSE) evaluation metric, we find that forecasting sales with the SARIMA method offers the best performance, on average, relative to the other compared methods. To support the findings, both mathematical and economic reasoning on the drivers of the observed performance for each method are provided. However, a decision maker or an organization need to evaluate the trade-off between forecasting accuracy and the shortcomings associated with each method.
Costly Actions, External Incentives and Prediction Markets
(University of Waterloo, 2017-08-25) Di, Chen; Dimitrov, Stanko; He, Qi-Ming
Consider a prediction market of multiple rounds with a security contingent on a certain event whose final outcome is decided by the agents who also trade in the market. One such prediction market is one in which two agents, Alice and Bob, are trading on the likelihood of a project both are working on complete. Prior research either only considers the expected rewards in the prediction market or if external incentives are present, then only a low number of rounds in the prediction market, to our knowledge at most 2. In addition, the existing literature assumes that when external incentives exist, there is no net difference between the cost of different actions agents may take outside of the prediction market. For example, it is the same cost for either Alice to work hard to complete the project as it is for her to ``loaf'' and not work hard. In this work we consider a 2-round round setting in which agents' cost of external actions differ. We show that when external action costs differ but are within a proper range, a prediction market is incentive compatible regardless of the initial market estimate, something that currently is not shown in the existing literature.
Environmental taxation: The impact of carbon tax policy commitment on technology choice and social welfare
(University of Waterloo, 2020-12-17) Rustico, Erica; Dimitrov, Stanko
Motivated by multiple real-world settings, we determine a social welfare-maximizing regulator’s tax policies that induce a profit-maximizing polluting firm to make green technology choices. Using a game-theoretic approach we compare the optimal tax and social welfare over two periods under two scenarios: (1) a regulator committing to a tax level for both periods at the beginning of the first period; (2) a regulator who sets the same tax at the beginning of each period without disclosing this information to the firm (i.e. the firm is not aware of the second period tax in the first period). We find that regulators can achieve a higher social welfare when two-period commitments are made. Moreover, the outcomes in the commitment policy are less sensitive to small deviations in the optimal tax level.
Essays in Corporate Prediction Markets
(University of Waterloo, 2017-08-22) Karimi, Majid; Dimitrov, Stanko
Personal subjective opinions are one of the most important assets in management. Prediction markets are mechanisms that can be deployed to elicit and aggregate a group of people’s opinions regarding the outcome of future events at any point in time. Prediction markets are exchange-traded markets where security values are tied to the outcome of future events. Prediction markets are systematically designed in a way that their market prices capture the crowd’s consensus about the probability of a future event. Corporations harness internal prediction markets for managerial decision making and business forecasting. Prediction markets are traditionally designed for large and diverse populations, two properties that are not often displayed in corporate settings. Therefore special considerations must be given to prediction markets used in corporations. Our first contribution in this thesis is in addressing the issue of diversity, in the sense of risk preferences, in corporate prediction markets. We study prediction markets in the presence of risk averse or risk seeking agents that have unknown risk preferences. We show that such agents’ behavior is not desirable for the purpose of information aggregation. We then characterize the agents’ behavior with respect to prediction market parameters and offer a systematic method to market organizers that fine tunes market parameters so at to best mitigate the impact of a pool agents’ risk-preferences. Our Second contribution in this thesis is in recommending prediction market mechanisms in different settings. There are many prediction market mechanisms with various advantages and weaknesses. The choice of a market mechanism can heavily affect the market accuracy and in turn, the success of a managerial decision, or a forecast based on prediction markets’ prices. Using trade data from two real-world prediction markets, we study the two main types of prediction markets mechanism and provide the much-needed insight as to what market mechanism to choose in various situations.
Essays on building and evaluating two-stage DEA models of efficiency and effectiveness
(University of Waterloo, 2021-07-27) Attarwala, Abbas; Dimitrov, Stanko
Researchers are not consistent in their choice of input and output variables when using two-stage data envelopment analysis (DEA) models to measure efficiency and effectiveness. This inconsistency has resulted in the development of many different two-stage DEA models of efficiency and effectiveness for the financial industry. In this dissertation, I improved the statistical method from the MASc dissertation (Attarwala, 2016) by adding more features. These features are documented in Chapter 2 on page 4 and page 5. This statistical method evaluates efficiency and effectiveness models in the banking industry. It relies on the semi-strong version of the efficient market hypothesis (EMH). The EMH is motivated by the wisdom of the crowds, discussed in Section 2.2.2. Previously (Attarwala, 2016), I found that the two-stage DEA model of Kumar and Gulati (2010) is not consistent with the semi-strong EMH for Indian and American banks. In this dissertation, using my improved statistical method, I show that the two-stage DEA model of Kumar and Gulati (2010) is not consistent with the semi-strong EMH for banks in Brazil, Canada, China, India, Japan, Mexico, South Korea and the USA from 2000- 2017. I address the question of whether a universal two-stage DEA model of efficiency and effectiveness exists by building a variable selection framework. This variable selection framework automatically generates two-stage DEA models of efficiency and effectiveness. To do this, it uses the improved statistical method and a genetic search (GS) algorithm. The variable selection framework finds the best, universal, two-stage DEA model of efficiency and effectiveness consistent with the semi-strong definition of EMH for banks in Brazil, Canada, China, India, Japan, Mexico, South Korea and the USA and from 2000-2017. I investigated the causal relationship between (a) the quantitative measures of efficiency and effectiveness from the best two-stage DEA model generated by the variable selection framework and (b) Tobin’s Q ratio, a financial market-based measure of bank performance. Not only do I provide bank managers with a reasonable proxy for measuring efficiency and effectiveness, but I also address the question of whether acting on these input and output variables improves the performance of banks in the financial market. Finally, I set up an optimization problem and find an optimal path from the two-stage DEA model of Kumar and Gulati (2010) to the best two-stage DEA model found by the variable selection framework. This optimal path provides a set of actionable items for converting a two-stage DEA model that is not consistent with the semi-strong EMH to one that is.
The Impacts of Climate Change via Robust Optimization: Two Applications in Land Investment and Electricity Storage Systems
(University of Waterloo, 2024-01-03) WU, ZHENGGAO; Dimitrov, Stanko; Pavlin, Michael
Effectively adapting to a changing climate involves making appropriate operational decisions based on long-term climate forecasts. This dissertation presents a comprehensive framework that combines climate data, regression models, and robust optimization models to examine the decision-making process for adapting to climate change over long time horizons. The research includes two projects: one focuses on studying land investment decisions, and the other investigates the operations of electricity storage systems, both considering the impacts of climate change. Project 1: Climate change affects agricultural inputs, like temperature and precipitation, and further affects the economic output of farmland. In this study, we focus on formulating effective policies to aid various stakeholders, including investors and farmers, in adapting to the climate-induced impacts on farmland investment in the Mississippi River Basin (MRB) by using well-known climate models. Each climate model generates a unique climate forecast, and based on these forecasts, we compute a range of farmland values for the MRB. Utilizing these ranges, we apply a robust optimization model to study the optimal investment policies under varying levels of conservatism, representing the extent to which farmland assets are constrained to adopt worst-case values. We show that the optimization model can be linearized and can scale to long time frames, about 50-plus years, and sets of assets. The case study of investment in the MRB covers the years 2023-2090 and uses trajectories of land values determined for each climate scenario using a regression model. Our empirical study shows that there is a disagreement between popular climate forecasts that influence land investment and may affect the most profitable land investments. Project 2: The effects of climate change on energy markets are diverse, encompassing changes in demand patterns and supply dynamics, particularly concerning the increasing penetration of renewable energy. These changes impact the dynamics of energy supply from renewable sources, such as wind and solar, leading to increased intermittency. Battery energy storage systems (BESSs) present a promising solution to effectively manage this intermittency from renewable energy sources. However, their profitability and incentive to participate in markets under climate change are susceptible to both the magnitude and frequency of price variation. This project investigates the impact of climate change on a BESS operating in a North American deregulated electricity market. We propose a robust optimization model to determine the operating policy of a BESS over 80 years (from 2021 to 2100) under different climate projections. We reformulate the robust optimization model to an equivalent linear program that allows us to numerically explore the operations of the BESS over the time horizon. Our empirical study analyzes the optimal arbitrage operations of the BESS in the Midcontinent Independent System Operator market in the United States, using the proposed robust model and trajectories of electricity prices determined for each climate scenario by a regression model. Additionally, we introduce a downscaling method to adjust climate scenarios to the desired resolutions for predicting electricity prices through the regression model. The results of the robust model reveal significant variations in the operating incomes of the BESS across different geographical locations and climate scenarios, highlighting the need for tailored strategies adapting to climate-induced variations in energy markets. The findings from both projects underscore the critical significance of considering a wide range of climate scenarios, encompassing detailed temporal and spatial data when assessing climate adaptation decisions.
Models of Deterministic and Stochastic Comparison: Two Studies in Applied Operations Research
(University of Waterloo, 2023-08-29) Burgess, Kiefer Joe; Dimitrov, Stanko; He, Qi-Ming
This dissertation includes two essays on applications of management science methods to modelling service systems and developing novel improvements to sports team ranking systems. The first essay proposes a novel approach to modelling changes in business procedures that have neither explicitly positive nor explicitly negative effects on operational performance, but are changes to operating rules; we call these procedure changes Operational Protocol Modifications (OPMs). Our approach is to model these OPMs via distributional censoring. Using the scenario of a technical support employee at a SaaS firm, we model changes in OPMs as censoring effects on the distributions of both service quality and service time. We demonstrate the nonlinear effects OPMs can have on the optimal service contract and the employer's (principal's) expected utility in hiring the technical support employee (agent), under certain distributional assumptions. This modelling approach arms operations management analysts with a new tool to better capture the impact of OPMs and their non-linear impacts on operational performance. The second essay proposes a number of additions to both static and dynamic network ranking models for professional soccer teams. We introduce ways to incorporate relevant home/away game status and goal difference information. Further, we introduce a collection of methods to measure the competitive similarity between teams, which we then integrate into the ranking systems. We demonstrate, using a large collection of data on five of the top European professional soccer leagues, that our methods produce superior empirical performance when compared to comparable approaches. Importantly, our work is the first to integrate the competitive similarity notion directly into network ranking models, providing the first direct link between two related bodies of literature.
Statistical Method of Goodness on Quantitative Models of Efficiency and Effectiveness
(University of Waterloo, 2016-08-17) Attarwala, Abbas; Dimitrov, Stanko; Obeidi, Amer
Motivated by different qualitative constructs of efficiency and effectiveness [Cameron, 1978] and the variety of distinct quantitative models of measuring efficiency and effectiveness derived from them, we propose a statistical method of goodness on these quantitative models in the financial setting. Our statistical method of goodness is based on the semi- strong Efficient Market Hypothesis (EMH) [Ball and Kothari, 1994]. The semi-strong form of the EMH claims that stock prices reflect all publicly available information and that stock prices instantly change to reflect new public information. Fi- nancial markets can identify firms that are effective, “doing the right things” and efficient, “doing things right.” A firm that is “doing the right things right” is both efficient and effective and the market should value such firms higher than other firms. In our statistical model, we use market information and its derivatives such as stock price, market capital and TobinQ [Perfect and Wiles, 1994] as dependent variables. Efficiency and effectiveness measures are considered as independent variables. Our statistical method finds the best fit model from a family of functions and reports model parameters that are statistically significant. We apply our statistical method of goodness on two case studies of US and Indian bank data. In these case studies, we use existing models of efficiency and effectiveness [Kumar and Gulati, 2009] and explore other [Chu and Lim, 1998] quantitative models of profit maximization and cost minimization efficiency and effectiveness.
Three Essays on Business Analytics: time-series causality, panel data analysis, and design of experiments
(University of Waterloo, 2020-05-13) Abolghasemi Dehaghani, Yaser; Dimitrov, Stanko
This dissertation includes three empirical studies focusing on the applications of Business Analytics in the context of financial markets and the online advertisement industry. The first essay examines the existence of a causal relationship between various prediction markets and global financial markets time series. This essay uses over 27 different countries and regions' financial market data (Dow Jones Global Indexes) and uses the Toda-Yamamoto causality test. Preliminary results indicate that prediction markets may be used to predict some global financial markets. From a managerial perspective, our result quantifies the connection between some countries' economy, as measured by a financial index, and the political events captured by the prediction markets we consider. The next two essays focus on the online advertising industry's business policies. The second essay uses a panel data analysis to compare the effect of two different IP protection policies, Monetize and Track, on YouTube music channels' viewership. This research provides insights for content owners on how IP protection policies on user-generated contents (UGCs) affect their YouTube channel viewership, and on how UGCs impact their ability to maximize profit. The third and final essay proposes a new data-driven statistical framework (DDSF) to determine what ad formats maximize a company's revenue generated from online advertising. The developed DDSF is applied in a real-world experiment. The experiment results help our YouTube industry partner determine what ad formats to run on their videos in order to trade off two key performance indicators of interest.
The use of data analytics to analyze various behaviors during the COVID- 19 pandemic
(University of Waterloo, 2024-05-24) AbdulHussein, Ali; Dimitrov, Stanko; Cozzarin, Brian
This dissertation outlines findings based on three journal manuscripts. The publications have a common theme: the use of data analytics techniques, economic theory, and knowledge of online shopping to analyze and assess change in behavior after the COVID-19 pandemic. I employed a variety of empirical analysis tools, including different regression methods, statistical analysis, and validity testing. I also utilized well-established theory to add another lens to my findings. Such frameworks include the Transaction Cost Economics (TCE) and the Technology Acceptance Model (TAM). Furthermore, I applied my tools to two domains to further widen my knowledge scope: e-commerce and public health. The first manuscript offered insight into consumer behavior after the COVID-19 pandemic. It analyzed the change in online shopping activity in 12 different product categories and offered an empirical association between it and various demographic factors. The second manuscript builds the first with more focus on online grocery shopping. As a result, the findings offered a managerial perspective on how various customer segments changed their shopping behaviors online, providing insight to guide marketing and merchandising efforts. The third paper presented an association between demographic and occupational factors with worsened mental health conditions of healthcare workers (HCWs) after the pandemic. The finding presented an insight into how different HCW groups reacted to the pandemic and hence aid in providing more effective mental health programming targeting specific groups in future events.

Browse

Browsing Management Science and Engineering by Author "Dimitrov, Stanko"